A Chosen Future Can Still Be Rewritten: Causal Writability in Video Models
Study shows video models often learn correct physics but fail to use it; low-dimensional 'causal writability' edits can restore correct motion.
The paper demonstrates 'causal writability' in video generation models: physically correct motion remains available inside the model even when the model outputs incorrect motion. In a red/blue mass oscillation setup, a low-dimensional edit predicted from simple physical variables restores correct fast motion, with a sharp depth boundary marking commitment. Early causal writability predicts which training errors later get corrected, and both writability and closure reproduce in a pretrained 1.3B video model.
- Correct motion often learned but unused; edits can restore it
- Sharp depth boundary marks commitment point for each edit
- Early causal writability predicts errors that later training corrects
- Reproduced in pretrained 1.3B video model, supporting generality
From the original article
1 min read at arxiv.orgWhen a video model generates physically incorrect motion, did it fail to learn the correct motion, or did it learn it but fail to use it? We show the latter: the correct motion remains available inside the model and can still be made to control the generated video. We train on videos where red masses oscillate slowly and blue masses oscillate quickly, then test a red mass with fast observed motion.
By Xingyun Wang · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.